Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies

Citations Over TimeTop 10% of 2013 papers

Abstract

The accurate and reliable prediction of properties of molecules typically requires computationally intensive quantum-chemical calculations. Recently, machine learning techniques applied to ab initio calculations have been proposed as an efficient approach for describing the energies of molecules in their given ground-state structure throughout chemical compound space (Rupp et al. Phys. Rev. Lett. 2012, 108, 058301). In this paper we outline a number of established machine learning techniques and investigate the influence of the molecular representation on the methods performance. The best methods achieve prediction errors of 3 kcal/mol for the atomization energies of a wide variety of molecules. Rationales for this performance improvement are given together with pitfalls and challenges when applying machine learning approaches to the prediction of quantum-mechanical observables.

Related Papers

• → Optimal measurements in quantum mechanics(2005)29 cited
• → The Role of Observables and Non-observables in Chemistry: A Critique of Chemical Language(2006)24 cited
• → Estimating the expectation values of spin-1/2 observables with finite resources(2007)18 cited
• → CALCULATION OF EXPECTED VALUES OF OBSERVABLES IN SOME PROBLEMS OF STATISTICAL GEOMORPHOLOGY(1971)1 cited
• → A Canonical form of Completely Uniformly Locally Weakly Observable Multi-output Nonlinear Systems(2006)